ID 原文 译文
45856 实验结果验证了 SPA 和 DPIOP 的隐私性能，与现有方法相比可减少能耗约为 63%，降低时延约为 35%。 Through simulation studies and experiments,the outstanding performance of SPA and DPIOP in privacy preservation were demonstrated, with saving energy by about63%, and reducing delay by about 35%.
45857 提出基于人工智能技术的多智能体服务链资源调度架构， A service chain resource scheduling architecture of multi-agent based on artificial intelligence technology was proposed.
45858 设计一种基于强化学习的服务链映射算法。 Meanwhile, a service chain mapping algorithm based on reinforcement learning was designed.
45859 通过 Q-learning 的机制，根据系统状态、执行部署动作后的奖惩反馈来决定服务链中各虚拟网元的部署位置。 Through the Q-learning mechanism, the location of each virtual network element in the service chain was determined according to the system status and the reward and punishment feedback after the deployment.
45860 实验结果表明，与经典算法相比，该算法有效降低了业务的平均传输延时，提升了系统的负载均衡情况。 The experimental results show that com-pared with the classical algorithms, the algorithm effectively reduces the average transmission delay of the service and improves the load balance of the system.
45861 为了使用尽可能少的 RSU 实现对目标区域的有效覆盖，设计 c 街道模型，将对区域的覆盖转化为对区域内街道的覆盖，然后，在该模型下提出基于贪心策略的多项式（GBP, greedy-based polynomial）时间近似算法，得到RSU的部署方案以解决覆盖问题。 To minimize the number of RSU deployed to cover a specific area, a c street model transforming the area covering problem to streets covering problem was designed, and a greedy-based polynomial (GBP) time approximation algorithm was developed to obtain the optimal RSU deployment for area coverage.
45862 针对城市中一些地形复杂的区域，设计Cue模型（complex urban environment model）， For complex urban environments, a Cuemodel (complex urban environments model) was proposed.
45863 将目标区域划分为子区域， In this model, the target area was divided into different partitions..
45864 然后提出基于 shifting 策略的多项式时间近似算法， Then, based on shifting strategy, a polynomial time approximation scheme was designed.
45865 并对算法的近似比率和时间复杂度进行了理论分析与证明。 Theoretical analysis that include the approximation ratio and time complexity of the proposed algorithm were also presented.